Special Reports

Weapons Technology

Buildings could save energy by spying on inhabitants

  • 28 April 2007
  • From New Scientist Print Edition. Subscribe and get 4 free issues.
  • Celeste Biever
Printable versionEmail to a friendRSS FeedSyndicate
 
 

A SMART building that monitors the movements of people inside it sounds like a way for your boss to spy on you. In fact, a building with a network of motion detectors can improve the energy efficiency and safety of the building while remaining deaf and blind to the activities of individuals.

Such systems could use their knowledge of where groups congregate to turn down the air conditioning when there are only a few people in one part of the building, for example. In an emergency, electronic signs could direct people to the nearest available escape route when one becomes congested.

Rather than using cameras, which would invade people's privacy, Christopher Wren at the Mitsubishi Electric Research Laboratory (MERL) in Cambridge, Massachusetts, is using "dumb" infrared motion sensors similar to those used to control automatic lights.

"Imagine peeling the roof off the building and watching people go about their lives, like in an ant farm," he says. "You can't identify individual ants or keep track of them as they scurry past each other, but you can watch as they move food into the nest or dig chambers."

"Imagine peeling the roof off and watching people go about their lives, like in an ant farm"

Wren fitted 215 wireless sensors to the ceilings of two floors of the MERL building and collected information from them over the course of a year. He also installed video cameras so he could match up the signals from the motion sensors with what movements were actually taking place, such as walking in a straight line, loitering, or people walking together or splitting apart.

He used his findings to program software to learn how signal patterns corresponded to different movements. When the software was then fed new motion data, it was able to accurately identify the movements 91 per cent of the time.

Wren has also programmed the software to detect patterns of movement that correspond to activities such as meetings. He has also programmed it to combine motion signals with information from other sources such as printer logs, to demonstrate that it can detect more complex actions like people collecting files from the printer.

 
From issue 2601 of New Scientist magazine, 28 April 2007, page 26
Comment subject
Comment
No HTML except lower case italic tags or lower case bold tags, please:
<i> or <b>
Your name
Your email
 

We need your email in case we need to contact you about the comment. We will not use it for any other purpose.

 
 

All comments should respect the New Scientist House Rules. If you think a particular comment breaks these rules then please use the "Report" link in that comment to report it to us.

If you are having a technical problem posting a comment, please contact technical support.

Printable versionEmail to a friendRSS FeedSyndicate
Cover of latest issue of New Scientist magazine
  • For exclusive news and expert analysis every week subscribe to New Scientist Print Edition
  • For what's in New Scientist magazine this week see contents
  • Search all stories
  • Contact us about this story
  • Sign up for our free newsletter
 
Password Login
Subscriptions